From e128f5703b37df4da4499b8ccb1164c428890243 Mon Sep 17 00:00:00 2001
From: Soraya Arias <soraya.arias@inria.fr>
Date: Fri, 6 Mar 2020 16:38:54 +0100
Subject: [PATCH] Propose to load the preloaded data in a comment
Former-commit-id: 0f4260eed78a606ee14053b984dce7e8321a730c
---
IMDB/01-Embedding-Keras.ipynb | 21 ++++++++++++---------
IMDB/03-LSTM-Keras.ipynb | 11 +++++++++--
2 files changed, 21 insertions(+), 11 deletions(-)
diff --git a/IMDB/01-Embedding-Keras.ipynb b/IMDB/01-Embedding-Keras.ipynb
index e990699..567cf00 100644
--- a/IMDB/01-Embedding-Keras.ipynb
+++ b/IMDB/01-Embedding-Keras.ipynb
@@ -169,13 +169,20 @@
"\n",
"# ----- Retrieve x,y\n",
"#\n",
+ "# Choose if you want to load dataset directly from keras (small size <20M)\n",
"(x_train, y_train), (x_test, y_test) = imdb.load_data( num_words = vocab_size,\n",
" skip_top = 0,\n",
" maxlen = None,\n",
" seed = 42,\n",
" start_char = 1,\n",
" oov_char = 2,\n",
- " index_from = 3, )"
+ " index_from = 3, )\n",
+ "# Or you can use the same pre-loaded dataset\n",
+ "#with h5py.File(f'{dataset_dir}/dataset_imdb.h5','r') as f:\n",
+ "# x_train = f['x_train'][:]\n",
+ "# y_train = f['y_train'][:]\n",
+ "# x_test = f['x_test'][:]\n",
+ "# y_test = f['y_test'][:]"
]
},
{
@@ -390,7 +397,7 @@
"cell_type": "markdown",
"metadata": {},
"source": [
- "### Save dataset and dictionary (For future use)"
+ "### Save dataset and dictionary (For future use but not mandatory if at GRICAD or IDRIS)"
]
},
{
@@ -407,15 +414,11 @@
}
],
"source": [
- "# ---- To write dataset in the project place\n",
- "#\n",
- "output_dir = dataset_dir\n",
- "\n",
- "# ---- To write h5 dataset in a test place\n",
+ "# ---- To write h5 dataset in a test place (optional)\n",
"# For small tests only !\n",
"#\n",
- "# output_dir = './data'\n",
- "# ooo.mkdir(output_dir)\n",
+ "output_dir = './data'\n",
+ "ooo.mkdir(output_dir)\n",
"\n",
"\n",
"with h5py.File(f'{output_dir}/dataset_imdb.h5', 'w') as f:\n",
diff --git a/IMDB/03-LSTM-Keras.ipynb b/IMDB/03-LSTM-Keras.ipynb
index 869ffdc..5684632 100644
--- a/IMDB/03-LSTM-Keras.ipynb
+++ b/IMDB/03-LSTM-Keras.ipynb
@@ -103,13 +103,20 @@
"\n",
"# ----- Retrieve x,y\n",
"#\n",
+ "# Choose if you want to load dataset directly from keras (small size <20M)\n",
"(x_train, y_train), (x_test, y_test) = imdb.load_data( num_words = vocab_size,\n",
" skip_top = 0,\n",
" maxlen = None,\n",
" seed = 42,\n",
" start_char = 1,\n",
" oov_char = 2,\n",
- " index_from = 3, )"
+ " index_from = 3, )\n",
+ "# Or you can use the same pre-loaded dataset if at GRICAD or IDRIS\n",
+ "#with h5py.File(f'{dataset_dir}/dataset_imdb.h5','r') as f:\n",
+ "# x_train = f['x_train'][:]\n",
+ "# y_train = f['y_train'][:]\n",
+ "# x_test = f['x_test'][:]\n",
+ "# y_test = f['y_test'][:]\n"
]
},
{
@@ -231,7 +238,7 @@
"cell_type": "markdown",
"metadata": {},
"source": [
- "### Save dataset and dictionary (can be usefull)"
+ "### Save dataset and dictionary (can be usefull but not mandatory if at GRICAD or IDRIS)"
]
},
{
--
GitLab